As Little as Possible, as Much as Necessary: Detecting Over-and Undertranslations with Contrastive Conditioning

Rico Sennrich, Jannis Vamvas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. If it links a repository, it is listed below.

Repositories linked to this paper

zurichnlp/coverage-contrastive-conditioning — marked official in Papers with Code; named in the paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Omission and addition of content is a typical issue in neural machine translation. We propose a method for detecting such phenomena with off-the-shelf translation models. Using contrastive conditioning, we compare the likelihood of a full sequence under a translation model to the likelihood of its parts, given the corresponding source or target sequence.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2203.01927")
get_code_for_paper("2203.01927")
have("2203.01927")

Connect an agent — have() is free.